AI agents use set_model_alias to create or update resources in MLflow MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MLflow MCP Server environment.
The tool modifies model metadata (aliases) in the MLflow model registry, which is a Write operation—it creates or updates state reversibly. While the description is empty, the name and context of sibling tools (which include read, write, and destructive operations on models and experiments) confirm this is a registry modification tool.
From the tool's definition Tool name 'set_model_alias' indicates modification of model aliases in MLflow registry. Sibling tools include destructive operations (delete_experiment, delete_model_version, delete_registered_model, delete_run), confirming this server manages critical ML…
Documented attack patterns abuse exactly the kind of access set_model_alias gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MLflow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for set_model_alias:
{
"version": "1",
"default": "deny",
"tools": {
"set_model_alias": {
"limits": [
{
"counter": "set_model_alias_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_model_alias stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
set_model_alias. It is categorised as a Write tool in the MLflow MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MLflow MCP Server MCP server in PolicyLayer and add a rule for set_model_alias: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MLflow MCP Server. Nothing to install.
set_model_alias is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_model_alias rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for set_model_alias. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
set_model_alias is provided by the MLflow MCP Server MCP server (kkruglik/mlflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MLflow MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
40 MLflow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.